Emergency resource allocation method, device and equipment for power distribution network under extreme rainstorm and medium

Abstract

This invention belongs to the field of emergency resource allocation technology, specifically relating to a method for allocating emergency resources in a power distribution network under extreme rainstorms. The method includes: collecting rainstorm event data; preprocessing the rainstorm event data to obtain a set of typical disaster scenarios and their corresponding probabilities; the set of typical disaster scenarios includes secondary disaster scenarios; inputting the set of typical disaster scenarios and their corresponding probabilities into a pre-constructed material demand model, which outputs a material reserve and cross-regional transportation plan; based on a pre-set emergency repair team capability profile model, outputting a plan for dividing emergency repair responsibility areas and allocating tasks; and obtaining an allocation plan based on the material reserve and cross-regional transportation plan, the responsibility area division, and the task allocation plan. This invention incorporates secondary disaster factors into typical disaster scenarios and clusters them, achieving rapid matching of material demands under typical equipment failures and typical disaster scenarios in the power distribution network by matching the probability of secondary disasters with equipment failure disaster scenarios.

Description

Technical Field

[0001] This invention belongs to the field of emergency resource allocation technology, specifically relating to methods, devices, equipment and media for emergency resource allocation in power distribution networks under extreme rainstorms. Background Technology

[0002] With the intensification of global climate change, extreme rainstorm disasters are becoming more frequent and highly destructive. Power distribution networks in complex terrain areas, such as mountainous, hilly, and river network areas, face prominent problems such as wide range of equipment damage, superimposed secondary disasters, and great difficulty in allocating emergency repair resources due to factors such as fragile geological conditions and limited transportation.

[0003] Existing studies on power grid disaster and fault scenario modeling mostly adopt single disaster parameter modeling, such as dividing the power supply area of ​​the distribution network into grids and simulating the impact of urban flooding on the distribution network through digital elevation models (DEM). However, secondary disasters will also occur under extreme rainstorms. The equipment failures caused by secondary disasters cannot be quantified. In the subsequent emergency resource allocation process, the matching degree of materials is low, and the repair efficiency of the repair teams is not commensurate, which easily leads to the waste of human resources. Summary of the Invention

[0004] The purpose of this invention is to provide a method, device, equipment and medium for emergency resource allocation in power distribution networks under extreme rainstorms, and to solve the problem of low efficiency in material allocation during the emergency resource allocation process in the background art.

[0005] To achieve the above objectives, the present invention adopts the following technical solution: In a first aspect, the present invention provides a method for emergency resource allocation in a power distribution network under extreme rainstorms, characterized in that it includes: Collect data on rainstorm events; The rainstorm event data is preprocessed to obtain a set of typical disaster scenarios and their corresponding probabilities; the set of typical disaster scenarios includes secondary disaster scenarios. The typical disaster scenario set and its corresponding probability are input into a pre-built material demand model, which outputs material reserve and cross-regional transportation plans. Based on a pre-defined capability profile model of the emergency repair team, output a plan for dividing emergency repair responsibility areas and allocating tasks. The allocation plan was obtained based on the material reserve and cross-regional transportation plan, the division of responsibility areas and the task allocation plan.

[0006] 2. The method for emergency resource allocation of power distribution networks under extreme rainstorms as described in claim 1, characterized in that the step of preprocessing the rainstorm event data to obtain a disaster scenario set and corresponding probabilities includes: Calculating the probability of secondary disasters based on rainstorm event data: Based on the probability of secondary disaster triggering, the conditional probability of the Bayesian network is updated to generate an initial disaster scenario set containing multi-dimensional feature vectors; The spatiotemporal evolution similarity between disaster scenarios in the initial disaster scenario set is calculated using a spectral clustering combined with a dynamic time warping algorithm. A similarity matrix is ​​constructed based on the spatiotemporal evolution similarity between disaster scenarios; Based on the similarity matrix, construct the Laplacian matrix; Solving the Laplacian matrix yields the eigenvectors corresponding to the first K smallest eigenvalues; The feature vectors are clustered to generate a set of typical disaster scenarios after clustering.

[0007] Preferably, the probability of secondary disaster triggering is calculated based on rainstorm event data as follows: ; ; ; In the formula: The intensity of rainstorm disasters includes the maximum hourly rainfall. Water depth and topographic elevation gradient ; Secondary disaster events; This refers to the time decay weighting parameter; The decay rate is taken as an empirical value of 0.1 to 0.3; t is the time variable; T is the maximum time period. As an indicator function, when the intensity of the rainstorm disaster varies over time... t Internal triggering of secondary disasters The value is 1 if the condition is met, and 0 otherwise. The indicator function is the intensity of rainstorm disasters. The value is 1 when the preset threshold is reached or exceeded, and 0 otherwise. This represents the total number of rainstorm events.

[0008] Preferably, the preprocessing step for the rainstorm event data to obtain a set of typical disaster scenarios and corresponding probabilities includes: ; ; in: Information entropy is set for typical disaster scenarios; Entropy for the propagation of the disaster; Assign vulnerability weights to devices; This is the fault propagation time threshold; is the entropy weight adjustment factor; K is the total number of eigenvectors; This refers to a specific disaster event within a set of typical disaster scenarios.

[0009] Preferably, the typical disaster scenario set and its corresponding probabilities are input into a pre-constructed material demand model, and the material demand model outputs material reserve and cross-regional transportation plans in the following steps: The material demand model includes a first objective function and a second objective function; The first objective function is: ; In the formula: For each reserve point i Basic inventory level Total number of reserve points; This refers to the unit price of the goods. for i Minimum safe storage capacity of materials in the warehouse; The second objective function is: ; ; In the formula: Typical disaster scenarios s The probability of occurrence; S is the number of typical disaster scenarios; To the reserve point i To the point of demand j The unit cost of transporting materials; For disaster scenarios s From the reserve point i Transported to the point of demand j The quantity of materials is a decision variable; The unit out-of-stock penalty coefficient; For disaster scenarios s Lower Reserve Point i The shortage of supplies; the constraints are the supply demand constraint and the node constraint. i Supply and demand balance constraints, transportation capacity constraints, and non-negativity constraints; For disaster scenarios s Lower Reserve Point i The amount of surplus materials (unused inventory); For disaster scenarios s Lower Reserve Point i Total material demand in the jurisdiction; Additional material needs for emergency repairs in secondary disaster scenarios; The inherent material needs for emergency repairs of equipment malfunctions; For path i j Maximum transport capacity; For disaster scenarios s Bottom lane i j The probability of blocking.

[0010] Preferably, in the step of outputting the emergency repair responsibility area division and task allocation scheme based on the preset emergency repair team capability profile model, the emergency repair team capability profile model includes a third objective function and a fitness function; The third objective function is: ; In the formula: Time-economic weighting factor; Let f be a decision variable, representing a value of 1 if the fault point f is assigned to the emergency repair team t for handling, and 0 otherwise. This refers to the set of fault points within the area of ​​responsibility that need to be addressed. The repair time for the fault point after standardized processing; The set of load nodes within the area of ​​responsibility; The power outage loss of load node n after normalization; the constraint is as follows: ; The fitness function is: ; In the formula: , For fault i The time required for handling the situation and the time required for the team to move between the fault locations; m This represents the total number of fault points. n This represents the total number of load nodes. For load nodes j The losses due to power outages; This is the penalty coefficient for economic losses.

[0011] Preferably, the rainstorm event data collected includes the spatiotemporal distribution of rainfall intensity, topographic and geotechnical parameters, and equipment failure records.

[0012] In a second aspect, the present invention provides an emergency resource allocation device for a power distribution network under extreme rainstorms, comprising: The data acquisition module is used to collect data on rainstorm events. The preprocessing module is used to preprocess the rainstorm event data to obtain a set of typical disaster scenarios and their corresponding probabilities; the set of typical disaster scenarios includes secondary disaster scenarios. The first solution module is used to input the set of typical disaster scenarios and their corresponding probabilities into a pre-built material demand model, and the material demand model outputs material reserve and cross-regional transportation solutions. The second solution module is used to output a solution for dividing the emergency repair responsibility area and allocating tasks based on a pre-set emergency repair team capability profile model. The configuration module is used to obtain configuration schemes based on material reserves and cross-regional transportation plans, responsibility area division and task allocation plans.

[0013] In a third aspect, the present invention provides an electronic device, including a processor and a memory, wherein the processor is configured to execute a computer program stored in the memory to implement the aforementioned method for emergency resource allocation of power distribution networks under extreme rainstorms.

[0014] In a fourth aspect, the present invention provides a computer-readable storage medium storing at least one instruction that, when executed by a processor, implements the method for emergency resource allocation in a power distribution network under extreme rainstorms.

[0015] Compared with the prior art, the beneficial effects of the present invention are as follows: Secondary disaster factors are incorporated into typical disaster scenarios and clustered. Then, by real-time matching of secondary disaster probabilities with equipment failure disaster scenarios, rapid matching of material needs under typical equipment failure scenarios and typical disaster scenarios of power distribution networks can be achieved. Construct a task-driven material-team collaborative optimization mechanism, combining a sub-task rule base with the skill profiles of emergency repair teams, to achieve dynamic adaptation of resource allocation schemes with transportation accessibility and personnel efficiency in complex terrain. Attached Figure Description

[0016] The accompanying drawings, which form part of this application, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an undue limitation of the invention. In the drawings: Figure 1 This is a flowchart of an emergency resource allocation method for a power distribution network under extreme rainstorms, as described in Embodiment 1 of the present invention. Figure 2 This is a structural block diagram of an emergency resource allocation device for a power distribution network under extreme rainstorms, according to Embodiment 2 of the present invention. Figure 3 This is a structural block diagram of an electronic device according to Embodiment 3 of the present invention. Detailed Implementation

[0017] The present invention will now be described in detail with reference to the accompanying drawings and embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other.

[0018] The following detailed description is exemplary and intended to provide further detailed explanation of the invention. Unless otherwise specified, all technical terms used in this invention have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains. The terminology used in this invention is for the purpose of describing particular embodiments only and is not intended to limit the scope of exemplary embodiments according to the invention.

[0019] Example 1 like Figure 1 As shown, a method for emergency resource allocation in a power distribution network under extreme rainstorms includes the following specific steps: S1. Collect data on rainstorm events; The rainstorm event data includes the spatiotemporal distribution of rainfall intensity, topographic and geotechnical parameters, and equipment failure records.

[0020] S2. Preprocess the rainstorm event data to obtain a set of typical disaster scenarios and their corresponding probabilities; the set of typical disaster scenarios includes secondary disaster scenarios. The specific steps are as follows: Calculating the probability of secondary disasters based on rainstorm event data: ; ; ; In the formula: To correlate with the intensity of rainstorm disasters over time, including t Maximum hourly rainfall during the period Water depth and topographic elevation gradient ; Secondary disaster events, usually associated with There is a time lag; This is a time decay weight parameter that reflects the timeliness of the triggering relationship; the later the relationship occurs, the lower the weight. The decay rate is empirically set at 0.1 to 0.3. t The variable is time; T is the maximum time period. As an indicator function, when the intensity of the rainstorm disaster varies over time... t Internal triggering of secondary disasters The value is 1 if the condition is met, and 0 otherwise. The indicator function is the intensity of rainstorm disasters. The value is 1 when the preset threshold is reached or exceeded, and 0 otherwise. This represents the total number of rainstorm events.

[0021] Based on the probability of secondary disaster triggering, the conditional probability of the Bayesian network is updated to generate an initial disaster scenario set containing multi-dimensional feature vectors, specifically including: Based on historical disaster data and domain knowledge, a Bayesian network is constructed. The Bayesian network uses the rainfall intensity parameter as the root node, various secondary disasters (such as landslides and waterlogging) as intermediate nodes, and specific power grid equipment failures as leaf nodes. The directed connections between nodes represent the causal chain of disaster evolution. The initial conditional probabilities of the Bayesian network are obtained through training with historical data. During emergency response, the trigger probabilities of secondary disasters, calculated in real time, serve as new data input. A Bayesian update algorithm is employed to dynamically correct the corresponding conditional probabilities in the network using the new data, enabling the entire network to receive real-time observation information and adaptively adjust the correlation strength between various disaster-related components. ; In the formula: The real-time trigger probability is calculated by models such as the secondary disaster trigger probability based on the currently observed characteristics of the rainstorm. The updated conditional probability is a dynamic probability that incorporates historical experience and real-time evidence. Historical conditional probability; The learning rate is a parameter between 0 and 1. η The larger the value, the more the model relies on historical experience and the more conservative it is in adapting to changes; the smaller the value, the more sensitive it is to real-time evidence. This is used to balance the stability and adaptability of the model.

[0022] Probabilistic inference and scene generation are performed based on an updated dynamic Bayesian network. Real-time monitored rainstorm characteristic data is input into the network, and forward inference is performed using Monte Carlo sampling. In each round of sampling, based on the dynamic probability state of the current node, the occurrence of secondary disasters and equipment malfunctions are randomly simulated, generating a large number of random event chains that conform to the latest disaster evolution patterns. Each complete event chain constitutes an initial disaster scenario, and the state, intensity, and spatial information of various disasters and malfunctions contained within it are encapsulated into a structured multidimensional feature vector. All vectors together constitute the initial disaster scenario set used for subsequent optimization calculations. ; In the formula: It represents a geographic feature vector that integrates DEM elevation data, soil permeability, and slope stability coefficient, etc. Represents meteorological feature vectors; This represents the fault feature vector.

[0023] The spatiotemporal evolution similarity between disaster scenarios in the initial disaster scenario set is calculated using a spectral clustering combined with a dynamic time warping algorithm. ; ; In the formula: Similarity in spatiotemporal evolution between disaster scenarios; , They represent the first i , j Multidimensional feature sequences of a disaster scenario; For the set of aligned paths, satisfying endpoint alignment, monotonicity, and continuity constraints; p , q () represents a path node pair, indicating a disaster scenario sequence. The p A time slice and The q Time slice alignment; For multi-dimensional feature distances, Mahalanobis distance is used for calculation; The characteristic covariance matrix; This is the spatiotemporal alignment penalty factor.

[0024] Construct a similarity matrix based on the spatiotemporal evolution similarity between disaster scenarios. ; ; In the formula: For the first based on the Haversine formula i The geographic feature vector and the first j Topographic spatial correlation function of geographic feature vectors For smoothing parameters.

[0025] Based on the similarity matrix Construct the Laplace matrix; Perform eigenvalue decomposition on the Laplacian matrix and select the first... K The eigenvectors corresponding to the smallest eigenvalues; Solving for the Laplace matrix yields the previous... K The eigenvectors corresponding to the smallest eigenvalues; Cluster the feature vectors to generate K Typical disaster scenarios of the class Each type of disaster scenario s It includes equipment failure combinations, secondary disaster types, and traffic disruption patterns.

[0026] Considering all fault scenarios of the distribution network under a rainstorm disaster during the solution process would result in a massive and complex computational problem, and would lack representativeness in practical analysis. Therefore, this application defines a node failure rate threshold and uses a non-sequential Monte Carlo sampling method to construct various secondary disaster fault scenarios of the distribution network under the entire process of a rainstorm disaster. Nodes with a failure rate greater than the threshold participate in the disaster scenario sampling, while nodes with a failure rate less than the threshold are not included in the sampling scope.

[0027] This application employs a combination of information entropy and disaster propagation entropy to optimize disaster scenario probabilities. Entropy values ​​are calculated for various fault disaster scenarios in the distribution network under various secondary disasters, and based on this, typical disaster scenario probabilities are selected. : ; ; in: Information entropy is used to represent the uncertainty of disaster events, based on a set of typical disaster scenarios. This is the catastrophe propagation entropy, used to quantify the intensity of a fault chain reaction. The equipment vulnerability weight is calculated based on the equipment's historical failure rate. The fault propagation time threshold is determined based on the power grid topology; is the entropy weight adjustment factor; K is the total number of eigenvectors; This refers to a specific disaster event within a set of typical disaster scenarios.

[0028] S3. Input the set of typical disaster scenarios and their corresponding probabilities into the pre-built material demand model, and the material demand model outputs material reserve and cross-regional transportation plans. The specific steps are as follows: To address typical secondary disasters caused by rainstorms, a rule base for mapping secondary disaster type, sub-task, and core material requirements has been established, as shown in Table 1: Table 1

[0029] The analytic hierarchy process (AHP) is used to quantify the priority of subtasks, and a material demand function is constructed by combining historical emergency repair records. ; In the formula: Indicates secondary disasters d Total material demand; R The total number of subtasks. For subtasks r The urgency weight is determined by expert scoring; for example, the obstacle clearing task. μ =0.8; , Subtask r Material demand parameters area and volume V The influence coefficient.

[0030] The above model only covers the materials needed for secondary disasters. Additional sub-tasks and material requirements for different equipment failures also need to be considered.

[0031] To address faults in core equipment of the distribution network, a rule base for mapping equipment type, emergency repair sub-task, and additional material requirements is established, as shown in Table 2: Table 2

[0032] Constructing an association matrix based on fault tree analysis, consisting of equipment type, emergency repair sub-task, and additional material requirements. ,in N According to the types of supplies, K Total material requirements for each type of emergency repair sub-task The calculation is as follows: ; In the formula: The frequency vector for triggering emergency repair subtasks is generated from historical fault statistics.

[0033] Typical disaster scenario set Probability-weighted sampling Given several reserve points, establish a primary objective function. By solving this function, determine the basic inventory at each reserve point to ensure sufficient material reserves at the lowest cost, thus obtaining a material reserve plan. ; In the formula: For each reserve point i Basic inventory level Total number of reserve points; This refers to the unit price of the goods. for i Minimum safe storage capacity of materials in the warehouse.

[0034] Based on actual disaster scenarios s Solve the second objective function to obtain the cross-regional transportation plan, while allowing for a small amount of shortage to cope with extreme situations.

[0035] The second objective function is defined as the dynamic adjustment phase, which obtains cross-regional transportation solutions based on the material shortages in sampled disaster scenarios: ; The constraints of the second objective function are: ; In the formula: For disaster scenarios s The probability of occurrence; S is the number of typical disaster scenarios; To the reserve point i To the point of demand j The unit cost of transporting materials; For disaster scenarios s From the reserve point i Transported to the point of demandj The quantity of materials is a decision variable; The unit out-of-stock penalty coefficient; For disaster scenarios s Lower Reserve Point i The amount of supplies out of stock; The constraints are material demand constraints and node constraints. i Supply and demand balance constraints, transportation capacity constraints, and non-negativity constraints; For disaster scenarios s Lower Reserve Point i The amount of surplus materials (unused inventory); For disaster scenarios s Lower Reserve Point i Total material demand in the jurisdiction; Additional material needs for emergency repairs in secondary disaster scenarios; The inherent material needs for emergency repairs of equipment malfunctions; For path i j Maximum transport capacity; For disaster scenarios s Bottom lane i j The probability of blocking.

[0036] S4. Based on the pre-set emergency repair team capability profile model, output the emergency repair responsibility area division and task allocation scheme; By using a simplified analytic hierarchy process, with technical ability (C1) and physical ability (C2) as the core criteria, and combining different disaster scenarios and equipment requirements, personnel are divided into skilled workers and unskilled workers according to their skills. Through an expert scoring mechanism, a profile of the repair team's repair efficiency in the disaster scenario is further obtained, providing a scientific basis for the estimation of repair time.

[0037] The criteria layer includes two indicators: technical ability C1 and physical ability C2. Technical skills refer to skills such as fault diagnosis and equipment debugging; physical skills refer to the ability to perform high-intensity tasks such as carrying and climbing.

[0038] The solution layer includes two categories: senior workers and junior workers. Senior workers have outstanding technical skills but weaker physical strength; junior workers have outstanding physical strength but weaker technical skills.

[0039] Through expert scoring, the efficiency coefficients of skilled workers and unskilled workers for C1 and C2 in a specific disaster scenario were obtained. α d , β d , α x , βx The corresponding relationships are shown in Table 3: Table 3

[0040] Assume the number of skilled workers in the emergency repair team is n The number of laborers is m The benchmark worker efficiency coefficients are α base β base Generally, the value is set to 1, which corresponds to the efficiency value of the emergency repair team. X eq for: ; The efficiency value represents the emergency repair capability profile of each team. The average efficiency of each team under a certain disaster scenario is rounded down to serve as the benchmark efficiency value for that disaster scenario. X base ; pass X eq / X base The repair efficiency of the emergency repair team in this disaster scenario can be calculated. η ; Finally, based on the benchmark emergency repair time T base It can provide the estimated repair time for the emergency repair team in a fault or disaster scenario. T exp : ; Based on capability profiles, Voronoi diagrams are used to solve for the third objective function to divide responsibility regions, resulting in the divided responsibility regions. The third objective function is: ; In the formula: Time-economic weighting factor; Let be the decision variable, representing the fault point. f Assigned to the emergency repair team t Use 1 for processing, otherwise use 0; This refers to the set of fault points within the area of ​​responsibility that need to be addressed. The set of load nodes within the area of ​​responsibility; For the load nodes after standardization n The power outage loss; the constraint is To avoid overloading.

[0041] As a preferred example of the above embodiments, the specific steps for dividing the responsibility region using Voronoi diagrams to solve the third objective function are as follows: Initial partitioning: The center points of the responsibility area are generated using a weighted K-means algorithm, with weights based on power outage losses. Obtain; Boundary optimization: Delaunay triangulation and A* algorithm are introduced to search for the optimal path and update the Voronoi cell boundary; Dynamic adjustment: Post-disaster adjustment based on real-time road network status With team load balance This triggers the merging or splitting of responsibility areas.

[0042] For each responsibility region, an improved genetic algorithm is used to solve the fitness function to obtain the task allocation scheme. The fitness function is: ; In the formula: , For fault i The time required for handling the situation and the time required for the team to move between the fault locations; m This represents the total number of fault points. n This represents the total number of load nodes. For load nodes j The losses due to power outages; This is the penalty coefficient for economic losses.

[0043] S5. The configuration plan is obtained based on the material reserve and cross-regional transportation plan, the division of responsibility areas and the task allocation plan.

[0044] Specifically, a material reserve and cross-regional transportation plan was adopted to ensure sufficient supplies, and a responsibility area division and task allocation plan was adopted for emergency repairs to complete the allocation of emergency resources.

[0045] Example 2 like Figure 2 As shown, based on the same inventive concept as the above embodiments, the present invention also provides an emergency resource allocation device for power distribution networks under extreme rainstorms, comprising: The data acquisition module is used to collect data on rainstorm events. The preprocessing module is used to preprocess the rainstorm event data to obtain a set of typical disaster scenarios and their corresponding probabilities; the set of typical disaster scenarios includes secondary disaster scenarios. The first solution module is used to input the set of typical disaster scenarios and their corresponding probabilities into a pre-built material demand model, and the material demand model outputs material reserve and cross-regional transportation solutions. The second solution module is used to output a solution for dividing the emergency repair responsibility area and allocating tasks based on a pre-set emergency repair team capability profile model. The configuration module is used to obtain configuration schemes based on material reserves and cross-regional transportation plans, responsibility area division and task allocation plans.

[0046] Example 3 like Figure 3 As shown, the present invention also provides an electronic device 100 for implementing a method for emergency resource allocation in a power distribution network under extreme rainstorms; The electronic device 100 includes a memory 101, at least one processor 102, a computer program 103 stored in the memory 101 and executable on at least one processor 102, and at least one communication bus 104.

[0047] The memory 101 can be used to store the computer program 103. The processor 102 implements the steps of the distribution network emergency resource allocation method under extreme rainstorms in Embodiment 1 by running or executing the computer program stored in the memory 101 and calling the data stored in the memory 101.

[0048] The memory 101 may primarily include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for at least one function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created based on the use of the electronic device 100 (such as audio data), etc. In addition, the memory 101 may include non-volatile memory, such as hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other non-volatile solid-state storage device.

[0049] At least one processor 102 may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Processor 102 may be a microprocessor or any conventional processor. Processor 102 is the control center of electronic device 100, connecting various parts of electronic device 100 via various interfaces and lines.

[0050] The memory 101 in the electronic device 100 stores multiple instructions to implement a method for emergency resource allocation in a power distribution network under extreme rainstorms, and the processor 102 can execute multiple instructions to achieve the following: Collect data on rainstorm events; The rainstorm event data is preprocessed to obtain a set of typical disaster scenarios and their corresponding probabilities; the set of typical disaster scenarios includes secondary disaster scenarios. The typical disaster scenario set and its corresponding probability are input into a pre-built material demand model, which outputs material reserve and cross-regional transportation plans. Based on a pre-defined capability profile model of the emergency repair team, output a plan for dividing emergency repair responsibility areas and allocating tasks. The allocation plan was obtained based on the material reserve and cross-regional transportation plan, the division of responsibility areas and the task allocation plan.

[0051] Example 4 If the modules / units integrated in the electronic device 100 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, and read-only memory (ROM).

[0052] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0053] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0054] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0055] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0056] In the description of this specification, references to terms such as "an embodiment," "example," "specific example," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0057] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for emergency resource allocation in power distribution networks under extreme rainstorms, characterized in that, include: Collect data on rainstorm events; The rainstorm event data is preprocessed to obtain a set of typical disaster scenarios and their corresponding probabilities; The typical disaster scenarios mentioned include secondary disaster scenarios; The typical disaster scenario set and its corresponding probability are input into a pre-built material demand model, which outputs material reserve and cross-regional transportation plans. Based on a pre-defined capability profile model of the emergency repair team, output a plan for dividing emergency repair responsibility areas and allocating tasks. The allocation plan was obtained based on the material reserve and cross-regional transportation plan, the division of responsibility areas and the task allocation plan.

2. The method for emergency resource allocation of power distribution networks under extreme rainstorms as described in claim 1, characterized in that, The step of preprocessing the rainstorm event data to obtain a set of typical disaster scenarios and their corresponding probabilities includes: Calculate the probability of secondary disasters based on rainstorm event data; Based on the probability of secondary disaster triggering, the conditional probability of the Bayesian network is updated to generate an initial disaster scenario set containing multi-dimensional feature vectors; The spatiotemporal evolution similarity between disaster scenarios in the initial disaster scenario set is calculated using a spectral clustering combined with a dynamic time warping algorithm. A similarity matrix is ​​constructed based on the spatiotemporal evolution similarity between disaster scenarios; Based on the similarity matrix, construct the Laplacian matrix; Solving the Laplacian matrix yields the eigenvectors corresponding to the first K smallest eigenvalues; Cluster the feature vectors to generate a clustered set of typical disaster scenarios. .

3. The method for emergency resource allocation of power distribution networks under extreme rainstorms as described in claim 2, characterized in that, The calculation of the probability of secondary disasters based on rainstorm event data. for: ； ； ； In the formula: The intensity of rainstorm disasters includes the maximum hourly rainfall. Water depth and topographic elevation gradient ; Secondary disaster events; This refers to the time decay weighting parameter; The decay rate is taken as an empirical value of 0.1 to 0.3; t is the time variable; T is the maximum time period. As an indicator function, when the intensity of the rainstorm disaster varies over time... t Internal triggering of secondary disasters The value is 1 if the condition is met, and 0 otherwise. The indicator function is the intensity of rainstorm disasters. The value is 1 when the preset threshold is reached or exceeded, and 0 otherwise. This represents the total number of rainstorm events.

4. The method for emergency resource allocation of power distribution networks under extreme rainstorms as described in claim 3, characterized in that, The rainstorm event data is preprocessed to obtain the probabilities corresponding to typical disaster scenarios. ,include: ； ； in: Information entropy is set for typical disaster scenarios. For the entropy of catastrophe propagation, As a weight for device vulnerability, This is the fault propagation time threshold; is the entropy weight adjustment factor; K is the total number of eigenvectors; This refers to a specific disaster event within a set of typical disaster scenarios.

5. The method for emergency resource allocation of power distribution networks under extreme rainstorms as described in claim 1, characterized in that, The typical disaster scenario set and its corresponding probabilities are input into a pre-constructed material demand model, which outputs material reserve and cross-regional transportation plans. The material demand model includes a first objective function and a second objective function; The first objective function is: ； In the formula: For each reserve point i Basic inventory level Total number of reserve points; This refers to the unit price of the goods. for i Minimum safe storage capacity of materials in the warehouse; The second objective function is: ； ； In the formula: Typical disaster scenarios s The probability of occurrence; S represents the number of typical disaster scenarios; To the reserve point i To the point of demand j The unit cost of transporting materials; For disaster scenarios s From the reserve point i Transported to the point of demand j The quantity of materials is a decision variable; The unit out-of-stock penalty coefficient; For disaster scenarios s Lower Reserve Point i The shortage of supplies; the constraints are the supply demand constraint and the node constraint. i Supply and demand balance constraints, transportation capacity constraints, and non-negativity constraints; For disaster scenarios s Lower Reserve Point i The amount of surplus materials; For disaster scenarios s Lower Reserve Point i Total material demand in the jurisdiction; Additional material needs for emergency repairs in secondary disaster scenarios; The inherent material needs for emergency repairs of equipment malfunctions; For path i j Maximum transport capacity; For disaster scenarios s Bottom lane i j The probability of blocking.

6. The method for emergency resource allocation of power distribution networks under extreme rainstorms as described in claim 1, characterized in that, In the step of outputting the emergency repair responsibility area division and task allocation scheme based on the preset emergency repair team capability profile model, the emergency repair team capability profile model includes a third objective function and a fitness function. The third objective function is: ； In the formula: Time-economic weighting factor; Let be the decision variable, representing the fault point. f Assigned to the emergency repair team t Use 1 for processing, otherwise use 0; This refers to the set of fault points within the area of ​​responsibility that need to be addressed. The repair time for the fault point after standardized processing; The set of load nodes within the area of ​​responsibility; For the load nodes after standardization n The power outage loss; the constraint is ; The fitness function is: ； In the formula: , For fault i The time required for handling the situation and the time required for the team to move between the fault locations; m This represents the total number of fault points. n This represents the total number of load nodes. For load nodes j The losses due to power outages; This is the penalty coefficient for economic losses.

7. The method for emergency resource allocation of power distribution networks under extreme rainstorms as described in claim 1, characterized in that, The collected rainstorm event data includes the spatiotemporal distribution of rainfall intensity, topographic and geotechnical parameters, and equipment failure records.

8. An emergency resource allocation device for power distribution networks under extreme rainstorms, characterized in that: include: The data acquisition module is used to collect data on rainstorm events. The preprocessing module is used to preprocess the rainstorm event data to obtain a set of typical disaster scenarios and their corresponding probabilities; The typical disaster scenarios mentioned include secondary disaster scenarios; The first solution module is used to input the set of typical disaster scenarios and their corresponding probabilities into a pre-built material demand model, and the material demand model outputs material reserve and cross-regional transportation solutions. The second solution module is used to output a solution for dividing the emergency repair responsibility area and allocating tasks based on a pre-set emergency repair team capability profile model. The configuration module is used to obtain configuration schemes based on material reserves and cross-regional transportation plans, responsibility area division and task allocation plans.

9. An electronic device, characterized in that, It includes a processor and a memory, the processor being used to execute a computer program stored in the memory to implement the method for emergency resource allocation of power distribution networks under extreme rainstorms as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores at least one instruction, which, when executed by a processor, implements the method for emergency resource allocation of power distribution networks under extreme rainstorms as described in any one of claims 1 to 7.

Images